Zhisen graduated in Fall 2025. He developed and validated a deep-learning denoiser for GRAND-like radio data, showing that faint air-shower pulses can be recovered with substantially improved signal-to-noise-ratio and with more antennas retained for direction and energy reconstruction. He is now pursuing a PhD in machine learning at the University of Nebraska at Omaha.

Publication:  https://arxiv.org/abs/2602.03818

Sarvesh graduated in Fall 2025, his MSc thesis explored a new way to reconstruct the arrival directions of ultra high energy cosmic rays from radio array data. He combined air shower simulations with a physics-informed graph neural network within a simulation-based inference framework, showing that timing, amplitude, and polarization information can be folded into a single Bayesian reconstruction pipeline. He has been offered a PhD position at the University of Georgia.

Zach graduated in Summer 2025 and is now a staff engineer at SLAC National Accelerator Laboratory. His research developed a neural-Bayesian framework for reconstructing the directions of ultra-high-energy particles from nanosecond radio pulses with sub-degree precision, while explicitly accounting for bias. The work advances analysis methods for next-generation radio arrays such as GRAND, IceCube-Gen2, and AugerPrime Radio.

Publication: Phys.Rev.D 113 (2026) 6, 063018